Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1843 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1195. Min Range: -2.1195
Max Act: 2.1195. Min Act: -0.1700
Data Index: 7116346 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1195. Min Range: -2.1195
Max Act: 2.0356. Min Act: -0.1700
Data Index: 7377909 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1195. Min Range: -2.1195
Max Act: 2.0187. Min Act: -0.1700
Data Index: 7544101 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1195. Min Range: -2.1195
Max Act: 2.0356. Min Act: -0.1700
Data Index: 1412200 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1195. Min Range: -2.1195
Max Act: 2.0356. Min Act: -0.1700
Data Index: 3472583 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1195. Min Range: -2.1195
Max Act: 2.0356. Min Act: -0.1700
Data Index: 4832506 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1195. Min Range: -2.1195
Max Act: 2.0356. Min Act: -0.1700
Data Index: 7544104 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1195. Min Range: -2.1195
Max Act: 2.0187. Min Act: -0.1700
Data Index: 1156870 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1195. Min Range: -2.1195
Max Act: 2.0018. Min Act: -0.1700
Data Index: 3124020 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1195. Min Range: -2.1195
Max Act: 1.9849. Min Act: -0.1700
Data Index: 5964935 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1195. Min Range: -2.1195
Max Act: 1.9849. Min Act: -0.1700
Data Index: 7003562 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1195. Min Range: -2.1195
Max Act: 1.9849. Min Act: -0.1700
Data Index: 6684663 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1195. Min Range: -2.1195
Max Act: 2.0018. Min Act: -0.1700
Data Index: 7612920 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1195. Min Range: -2.1195
Max Act: 1.9849. Min Act: -0.1700
Data Index: 243791 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1195. Min Range: -2.1195
Max Act: 1.9680. Min Act: -0.1700
Data Index: 1793530 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1195. Min Range: -2.1195
Max Act: 1.9680. Min Act: -0.1700
Data Index: 5105619 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1195. Min Range: -2.1195
Max Act: 1.9510. Min Act: -0.1700
Data Index: 4124403 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1195. Min Range: -2.1195
Max Act: 1.9849. Min Act: -0.1700
Data Index: 587189 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1195. Min Range: -2.1195
Max Act: 1.9510. Min Act: -0.1700
Data Index: 1875961 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1195. Min Range: -2.1195
Max Act: 1.9510. Min Act: -0.1700
Data Index: 6632753 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19